Product Purchase Prediction

  • Tech Stack: Python, Streamlit, Pandas, Scikit-learn, Plotly, Matplotlib, Seaborn
  • Github URL: Project Link
  • Developed Under: CipherSchools Summer Training Program

Project Overview

This project showcases the application of machine learning in analyzing and predicting customer behavior in an e-commerce setting. Built as part of the CipherSchools Summer Training Program, it leverages data such as time spent on site, customer demographics, and interaction history to make purchase predictions. The accuracy is relatively low due to the small dataset used.

Features

  • Interactive Dashboard: Streamlit-based UI for real-time interaction
  • Data Analysis: Visual exploration of user behavior
  • ML Models: Logistic Regression and Decision Tree Classifier
  • Real-Time Prediction: Predict purchase intent on-the-fly
  • Batch Prediction: Analyze multiple customer records at once
  • Customer Segmentation: Insightful breakdown for marketing strategies

Technical Stack

  • Frontend: Streamlit with custom styling
  • Data Manipulation: Pandas
  • Machine Learning: Scikit-learn
  • Visualization: Plotly, Matplotlib, Seaborn

Setup Instructions

To run the project locally, follow these steps:

  1. Clone the repository from GitHub
  2. Navigate to the project directory
  3. Install the required dependencies:
    4. pip install -r requirements.txt
  4. Run the Streamlit application:
    5. streamlit run app.py